@inproceedings{barkarson-etal-2022-evolving,
title = "Evolving Large Text Corpora: Four Versions of the {I}celandic {G}igaword Corpus",
author = "Barkarson, Starka{\dh}ur and
Steingr{\'\i}msson, Stein{\th}{\'o}r and
Hafsteinsd{\'o}ttir, Hildur",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.254",
pages = "2371--2381",
abstract = "The Icelandic Gigaword Corpus was first published in 2018. Since then new versions have been published annually, containing new texts from additional sources as well as from previous sources. This paper describes the evolution of the corpus in its first four years. All versions are made available under permissive licenses and with each new version the texts are annotated with the latest and most accurate tools. We show how the corpus has grown almost 50{\%} in size from the first version to the fourth and how it was restructured in order to better accommodate different meta-data for different subcorpora. Furthermore, other services have been set up to facilitate usage of the corpus for different use cases. These include a keyword-in-context concordance tool, an n-gram viewer, a word frequency database and pre-trained word embeddings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="barkarson-etal-2022-evolving">
<titleInfo>
<title>Evolving Large Text Corpora: Four Versions of the Icelandic Gigaword Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Starka\dhur</namePart>
<namePart type="family">Barkarson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stein\thór</namePart>
<namePart type="family">Steingrímsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hildur</namePart>
<namePart type="family">Hafsteinsdóttir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The Icelandic Gigaword Corpus was first published in 2018. Since then new versions have been published annually, containing new texts from additional sources as well as from previous sources. This paper describes the evolution of the corpus in its first four years. All versions are made available under permissive licenses and with each new version the texts are annotated with the latest and most accurate tools. We show how the corpus has grown almost 50% in size from the first version to the fourth and how it was restructured in order to better accommodate different meta-data for different subcorpora. Furthermore, other services have been set up to facilitate usage of the corpus for different use cases. These include a keyword-in-context concordance tool, an n-gram viewer, a word frequency database and pre-trained word embeddings.</abstract>
<identifier type="citekey">barkarson-etal-2022-evolving</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.254</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>2371</start>
<end>2381</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evolving Large Text Corpora: Four Versions of the Icelandic Gigaword Corpus
%A Barkarson, Starka\dhur
%A Steingrímsson, Stein\thór
%A Hafsteinsdóttir, Hildur
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F barkarson-etal-2022-evolving
%X The Icelandic Gigaword Corpus was first published in 2018. Since then new versions have been published annually, containing new texts from additional sources as well as from previous sources. This paper describes the evolution of the corpus in its first four years. All versions are made available under permissive licenses and with each new version the texts are annotated with the latest and most accurate tools. We show how the corpus has grown almost 50% in size from the first version to the fourth and how it was restructured in order to better accommodate different meta-data for different subcorpora. Furthermore, other services have been set up to facilitate usage of the corpus for different use cases. These include a keyword-in-context concordance tool, an n-gram viewer, a word frequency database and pre-trained word embeddings.
%U https://aclanthology.org/2022.lrec-1.254
%P 2371-2381
Markdown (Informal)
[Evolving Large Text Corpora: Four Versions of the Icelandic Gigaword Corpus](https://aclanthology.org/2022.lrec-1.254) (Barkarson et al., LREC 2022)
ACL